def convert_cols_to_lines(p_source_dir, p_source_file, p_destination_dir,
p_dest_file_list, p_individualsposlist,
p_gen_column):
utils.log(logger, "Begin - convert_gen_cols_to_ind_lines - ")
positionindex = p_individualsposlist.index(p_gen_column)
regex = r"^{0}.*{1}$".format(
p_destination_dir + "IND_" + str(positionindex + 1) + "_",
destination_file_type)
p_indfilename = utils.find_file_in_list(p_dest_file_list, regex)
source_file = utils.get_file_name(str(p_source_file))
try:
col = int(p_gen_column)
except:
e = sys.exc_info()[0]
utils.log(logger, e)
#Open individuals file
with open(p_indfilename, 'a') as indfile:
utils.log(logger, "Writing IND .tsv file: " + p_indfilename)
csvwriter = csv.writer(indfile,
delimiter='\t',
quotechar='"',
quoting=csv.QUOTE_MINIMAL)
sequence = 0
with gzip.open(p_source_dir + p_source_file, 'rb') as genfile:
for line in genfile: #reads line by line .gen file.
#readlines() loads full .gen file into memory and split in lines. To many threads
# or very big files can cause memory overflow.
#for line in genfile.readlines():
sequence = sequence + 1
seq = str(sequence).split()
columns = line.split()
csvwriter.writerow([source_file] + seq + columns[col:col + 3])
indfile.close()
utils.log(logger, "Lines in source file: " + str(sequence))
genfile.close()
utils.log(logger, "End - convert_gen_cols_to_ind_lines - ")
return
def convert_cols_to_lines(p_source_dir,p_source_file,p_destination_dir,p_dest_file_list, p_individualsposlist, p_gen_column):
utils.log(logger,"Begin - convert_gen_cols_to_ind_lines - ")
positionindex = p_individualsposlist.index(p_gen_column)
regex = r"^{0}.*{1}$".format(p_destination_dir+"IND_"+str(positionindex+1)+"_",destination_file_type)
p_indfilename = utils.find_file_in_list(p_dest_file_list,regex)
source_file = utils.get_file_name(str(p_source_file))
try:
col = int(p_gen_column)
except:
e = sys.exc_info()[0]
utils.log(logger,e)
#Open individuals file
with open(p_indfilename,'a') as indfile:
utils.log(logger,"Writing IND .tsv file: "+ p_indfilename)
csvwriter = csv.writer(indfile,delimiter='\t',quotechar='"', quoting=csv.QUOTE_MINIMAL)
sequence = 0
with gzip.open(p_source_dir+p_source_file,'rb') as genfile:
for line in genfile: #reads line by line .gen file.
#readlines() loads full .gen file into memory and split in lines. To many threads
# or very big files can cause memory overflow.
#for line in genfile.readlines():
sequence=sequence+1
seq=str(sequence).split()
columns=line.split()
csvwriter.writerow([source_file]+seq+columns[col:col+3])
indfile.close()
utils.log(logger,"Lines in source file: "+ str(sequence))
genfile.close()
utils.log(logger,"End - convert_gen_cols_to_ind_lines - ")
return
batchPlaceholders = utils.make_placeholders(subarrayPos, nbBatches)
headerPlaceholders = utils.make_headers("batch", 0, nbBatches)
f = cursor.fetchone()
current_id = -1
migratedindividuals=0
utils.log(logger, "Writing <<Individuals>> files")
utils.log(logger, "------------------------------------")
while f:
current_id = f[0]
if importGenotypesFlag == "Y":
regex = r"^SAM_[0-9]+_{0}_.*{1}$".format(current_id,file_type_oxford)
filename = utils.find_file_in_list(sourcesFileList, regex)
familyID = ''
fatherID = ''
motherID = ''
if filename == None:
utils.log(logger, "ID: "+str(current_id) +" -Not found in SAMPLE file")
else:
os.makedirs(output_dir + str(current_id))
with open("{0}{1}/Individuals_{1}.tsv".format(output_dir, current_id), "w") as file:
file.write("individualId,familyId,paternalId,maternalId,dateOfBirth,gender,ethnicCode,centreName,region,country,notes,missingCallFreq,{0}\n".format(headerPlaceholders))
familyID=utils.get_individual_info(sourcesDirectory+filename, "ID_2")
fatherID=utils.get_individual_info(sourcesDirectory+filename, "father")
motherID=utils.get_individual_info(sourcesDirectory+filename, "mother")
batchPlaceholders = utils.make_placeholders(subarrayPos, nbBatches)
headerPlaceholders = utils.make_headers("batch", 0, nbBatches)
f = cursor.fetchone()
current_id = -1
migratedindividuals=0
utils.log(logger, "Writing <<Individuals>> files")
utils.log(logger, "------------------------------------")
while f:
current_id = f[0]
if importGenotypesFlag == "Y":
regex = r"^SAM_[0-9]+_{0}_.*{1}$".format(current_id,file_type_oxford)
filename = utils.find_file_in_list(sourcesFileList, regex)
familyID = ''
fatherID = ''
motherID = ''
if filename == None:
utils.log(logger, "ID: "+str(current_id) +" -Not found in SAMPLE file")
else:
os.makedirs(output_dir + str(current_id))
with open("{0}{1}/Individuals_{1}.tsv".format(output_dir, current_id), "w") as file:
file.write("individualId,familyId,paternalId,maternalId,dateOfBirth,gender,ethnicCode,centreName,region,country,notes,missingCallFreq,{0}\n".format(headerPlaceholders))
familyID=utils.get_individual_info(sourcesDirectory+filename, "ID_2")
fatherID=utils.get_individual_info(sourcesDirectory+filename, "father")
motherID=utils.get_individual_info(sourcesDirectory+filename, "mother")
